INDEX

Explanations

help

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 missing

-0.30

 Fallen

-0.28

odi

-0.27

ewolf

-0.26

missing

-0.25

 Missing

-0.25

ypical

-0.25

tor

-0.24

Twe

-0.24

Firefox

-0.24

POSITIVE LOGITS

 privilege

0.28

æľīéĴ±

0.28

 Strap

0.28

 strap

0.28

ionario

0.26

å¥ĳæľº

0.26

åħ±çĶŁ

0.26

æīĽ

0.26

é£İåı£

0.25

è¿½éĹ®

0.25

Activations Density 0.008%

help

No Comments

No Known Activations