INDEX

Explanations

Only optionach

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

decoder

-0.30

hot

-0.28

ç»Ļ

-0.28

‘

-0.27

 decoder

-0.26

.fi

-0.26

æį¢

-0.26

 best

-0.25

èģĭ

-0.24

POSITIVE LOGITS

 bouts

0.29

emann

0.28

æĽ²

0.27

è¢«æīĵ

0.27

xit

0.27

ibo

0.27

 anale

0.26

&R

0.26

äºĭåĬ¡

0.26

osti

0.26

Activations Density 0.019%

Only optionach

No Comments

No Known Activations