INDEX

Explanations

width

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

echo

-0.27

eo

-0.25

dale

-0.25

ÑĢÐµÐ²

-0.24

GDK

-0.24

well

-0.23

pus

-0.23

VED

-0.23

<![

-0.23

ç¬Ļ

-0.23

POSITIVE LOGITS

less

0.25

 ÑĥÐ½Ð¸Ð²ÐµÑĢÑģ

0.25

 abound

0.25

 breadth

0.25

 picks

0.24

 Suff

0.24

 anniversary

0.24

ä¸Ģä»£

0.23

åĨ·éĿĻ

0.23

 broad

0.23

Activations Density 0.017%

width

No Comments

No Known Activations