INDEX

Explanations

Code and technical documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ATIC

-0.26

_KIND

-0.26

atic

-0.25

presso

-0.25

elia

-0.25

 Atom

-0.24

asted

-0.24

ç´°

-0.24

olly

-0.24

rita

-0.24

POSITIVE LOGITS

åĨĴ

0.28

 cá»ķ

0.28

ç¯Ļ

0.27

çĢĳå¸ĥ

0.27

iem

0.26

 runnable

0.25

 affirmation

0.25

-bs

0.25

åĴ«

0.25

ialized

0.24

Activations Density 0.001%

Code and technical documentation

No Comments

No Known Activations