INDEX

Explanations

Mixed sources of text

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

anta

-0.31

zÃ¡

-0.28

ivent

-0.27

å¼§

-0.26

ÃŃv

-0.26

nÄ±

-0.25

urn

-0.25

pÃµ

-0.25

ive

-0.25

 dÃ³

-0.24

POSITIVE LOGITS

çĸ

0.26

ç»Ħ

0.26

licer

0.26

ÑĩÐ¸

0.25

 recap

0.24

æķĳåĳ½

0.24

æĪĳéĥ½

0.23

_FUNCTIONS

0.23

.Fat

0.23

Activations Density 0.002%

Mixed sources of text

No Comments

No Known Activations