INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

iku

-0.31

é©º

-0.28

never

-0.27

 Ð´ÑĥÑħ

-0.26

oen

-0.26

mat

-0.26

å±Ĳ

-0.26

olist

-0.26

 never

-0.25

unist

-0.25

POSITIVE LOGITS

 pouring

0.28

 Pour

0.27

Men

0.27

Sus

0.26

utta

0.26

Åģ

0.25

æĬĢæľ¯åĴĮ

0.25

udget

0.25

 Paste

0.24

 pour

0.24

Activations Density 0.146%

punctuation

No Comments

No Known Activations