INDEX

Explanations

biological

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

raph

-0.29

 spaghetti

-0.27

andles

-0.26

 pencils

-0.26

 rides

-0.25

lem

-0.25

æĻļé¤Ĳ

-0.24

å¦«

-0.24

 skewed

-0.24

å¸Į

-0.24

POSITIVE LOGITS

Providers

0.27

/providers

0.27

elong

0.26

.Toolkit

0.25

ulong

0.25

ophys

0.25

Dry

0.24

µ¬

0.24

è§£åĨ³äºĨ

0.24

 behind

0.24

Activations Density 0.044%

biological

No Comments

No Known Activations