INDEX

Explanations

Technical writing/jargon

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĲľæķĳ

-0.27

oons

-0.26

 Cons

-0.26

 Sour

-0.26

mono

-0.25

Sur

-0.25

é¦Ĭ

-0.25

Cons

-0.25

 Parade

-0.25

 sour

-0.25

POSITIVE LOGITS

çĶ»åĥı

0.28

ä»Ĺ

0.27

Ã¼hr

0.27

cuts

0.27

gow

0.27

igm

0.27

 statewide

0.27

èĩªåĬ©

0.26

bsites

0.25

uess

0.25

Activations Density 0.257%

Technical writing/jargon

No Comments

No Known Activations