INDEX

Explanations

expert

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

LD

-0.28

LD

-0.26

PLACE

-0.25

[now

-0.25

 lens

-0.25

æľīæĿ¡ä»¶çļĦ

-0.24

ld

-0.24

rig

-0.23

 mixture

-0.23

ld

-0.23

POSITIVE LOGITS

ees

0.32

omo

0.32

è¿ĽäºĨ

0.28

gil

0.27

ousy

0.26

/english

0.26

omic

0.25

toast

0.25

olis

0.24

åħ¨æµģç¨ĭ

0.24

Activations Density 0.001%

expert

No Comments

No Known Activations