INDEX

Explanations

Computer/Software related

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

ann

-0.31

Ann

-0.25

ABA

-0.25

 placebo

-0.25

Verifier

-0.24

 come

-0.24

Ann

-0.23

 Canter

-0.23

åĩĨåĪĻ

-0.23

WXYZ

-0.23

POSITIVE LOGITS

 Destiny

0.32

 sorte

0.27

æľīä¸Ģç§į

0.26

ç¶ĵé©Ĺ

0.26

çļĦä¸Ģç§į

0.26

çĶ·åŃĲ

0.25

oeff

0.25

_party

0.25

ç¼Ģ

0.25

ç»ıéªĮ

0.25

Activations Density 0.002%

Computer/Software related

No Comments

No Known Activations