INDEX

Explanations

spray

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SCO

-0.31

tones

-0.28

.telegram

-0.27

 Meter

-0.26

uteur

-0.25

asion

-0.25

@show

-0.25

.Scope

-0.24

lify

-0.24

_SCOPE

-0.24

POSITIVE LOGITS

 growing

0.34

 Growing

0.32

dip

0.31

Growing

0.30

-growing

0.30

éĺ³

0.29

 nuÃ´i

0.29

 grow

0.29

mat

0.26

mat

0.26

Activations Density 0.009%

spray

No Comments

No Known Activations