INDEX

Explanations

Spooky

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çķ¸

-0.27

åĪĽéĢłæĢ§

-0.26

èĩª

-0.26

æĭĵ

-0.25

pickup

-0.25

 Ghost

-0.25

ghost

-0.25

ernet

-0.25

top

-0.24

utra

-0.24

POSITIVE LOGITS

 Propel

0.27

ç´¯

0.26

unta

0.26

 TSRMLS

0.26

<![

0.26

.documentation

0.25

quirer

0.25

çº°

0.25

 indifference

0.24

?p

0.24

Activations Density 0.916%

Spooky

No Comments

No Known Activations