INDEX

Explanations

think

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®¤å¤ĸ

-0.27

 vero

-0.26

 Kore

-0.26

/open

-0.25

Cr

-0.25

 rest

-0.25

é¡¶å±Ĥ

-0.24

è®¸åı¯

-0.24

epar

-0.24

kne

-0.24

POSITIVE LOGITS

extensions

0.27

_extension

0.27

 extension

0.27

itched

0.26

legacy

0.26

rac

0.25

 extensions

0.25

-fw

0.25

rac

0.24

extension

0.24

Activations Density 0.010%

think

No Comments

No Known Activations