INDEX

Explanations

hat

np_max-act · gemini-2.0-flash

mentions of hats, especially the exact word or its plural, including when embedded in longer terms or phrases.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 goog

-0.27

æ¯Ķè¾ĥå¤§

-0.26

æĢ§åĳ½

-0.26

 recap

-0.25

 eing

-0.25

æł¸å®ļ

-0.25

WXYZ

-0.24

 WithEvents

-0.24

_FILENAME

-0.24

éĵ°

-0.24

POSITIVE LOGITS

asty

0.31

tery

0.28

itioner

0.27

æĲł

0.26

åĩ¡

0.25

èĥ¤

0.25

astery

0.24

çĽĽä¸ĸ

0.24

á»ĩn

0.24

ptune

0.24

Activations Density 0.002%

hat

mentions of hats, especially the exact word or its plural, including when embedded in longer terms or phrases.

No Comments

No Known Activations