INDEX

Explanations

Numerical digits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĵªä¸Ģä¸ª

-0.28

ä»£

-0.26

FRING

-0.26

åĨįå¤ļ

-0.26

-even

-0.25

-common

-0.25

ãĦ§

-0.24

.logging

-0.24

 closely

-0.23

æĹ¥çĽĬ

-0.23

POSITIVE LOGITS

rib

0.27

åħĪå¯¼

0.27

ometrics

0.26

æ³Ħ

0.26

èĩªæľī

0.25

ãĢģ“

0.25

arah

0.24

 humour

0.24

pix

0.24

($)

0.24

Activations Density 0.007%

Numerical digits

No Comments

No Known Activations