INDEX

Explanations

0

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

åħ·

-0.32

è¿Ļæ¬¡

-0.27

rowse

-0.26

achten

-0.25

NY

-0.25

iske

-0.25

ieve

-0.25

+v

-0.24

 freel

-0.24

 Clown

-0.24

POSITIVE LOGITS

çĴľ

0.26

ernal

0.25

 signatures

0.24

/mat

0.24

harma

0.24

 bÄħdÅº

0.24

SIGN

0.24

 decre

0.24

 signer

0.24

é¹ĩ

0.23

Activations Density 0.006%

0

No Comments

No Known Activations