INDEX

Explanations

trauma

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

cock

-0.25

ell

-0.25

æĬĦ

-0.24

èĴĮ

-0.24

çģ¾

-0.24

 primaryKey

-0.24

cif

-0.24

/std

-0.24

ale

-0.24

elden

-0.24

POSITIVE LOGITS

udu

0.28

ffa

0.27

/apis

0.26

èµŀåĲĮ

0.25

_macros

0.25

ova

0.25

çĤ¹å¤´

0.25

gatsby

0.25

 glGet

0.24

ORS

0.24

Activations Density 0.361%

trauma

No Comments

No Known Activations