INDEX

Explanations

Heads

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

hani

-0.31

SPATH

-0.28

ional

-0.27

ICLES

-0.27

 Pistol

-0.26

 premiums

-0.26

oso

-0.25

 Ø§ÙĦØ£ÙĪÙĦÙī

-0.25

ç¬¬ä¸Ģä¸ª

-0.25

 dispose

-0.25

POSITIVE LOGITS

æİ¥

0.27

dra

0.26

itness

0.26

 Lama

0.25

stood

0.25

é¹³

0.24

 rave

0.24

 Äĳá»©ng

0.24

 stand

0.24

 evolutionary

0.24

Activations Density 0.001%

Heads

No Comments

No Known Activations