INDEX

Explanations

Report

np_max-act · gemini-2.0-flash

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

åįĵè¶Ĭ

-0.29

 patented

-0.28

 copyrighted

-0.27

ertz

-0.27

irty

-0.26

ennen

-0.26

[input

-0.25

ä¸īæľŁ

-0.25

olor

-0.25

NotSupportedException

-0.25

POSITIVE LOGITS

 setC

0.28

æĺ¯æĪĳ

0.27

ì¤Ħ

0.25

æĺ¯æľĢ

0.24

unist

0.24

 typeof

0.24

ä¸ŃæľĢ

0.24

_asm

0.24

wyn

0.23

 chunk

0.23

Activations Density 0.003%

Report

No Comments

No Known Activations