INDEX

Explanations

Star Trek

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

hek

-0.27

éĢĦ

-0.27

 things

-0.27

xing

-0.26

buz

-0.26

 finde

-0.25

dai

-0.25

Equ

-0.25

æĭ¿

-0.25

 cong

-0.24

POSITIVE LOGITS

BIND

0.27

AnimationFrame

0.26

abler

0.25

embr

0.25

è±¹

0.24

èħĶ

0.24

bnb

0.24

 informat

0.24

}\"

0.24

 BIND

0.23

Activations Density 0.014%

Star Trek

No Comments

No Known Activations