INDEX

Explanations

helping verbs

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

inet

-0.34

 warrants

-0.28

åı«æĪĳ

-0.27

æĬķèµĦé¡¹çĽ®

-0.26

unw

-0.25

ippy

-0.25

highlight

-0.25

omatic

-0.25

 scal

-0.24

Lov

-0.24

POSITIVE LOGITS

çļĦè¯Ŀé¢ĺ

0.27

ä¸Ńè¶ħ

0.27

//=

0.27

 resourceName

0.26

resource

0.25

Ã¤ren

0.25

prim

0.24

éĻªçĿĢ

0.24

_Generic

0.24

éĿ¢èī²

0.24

Activations Density 0.004%

helping verbs

No Comments

No Known Activations