INDEX

Explanations

gender

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

æľīè¿ĩ

-0.26

ods

-0.26

èĥ½æ»¡è¶³

-0.26

omat

-0.26

 MISS

-0.26

 disliked

-0.26

geries

-0.25

_gc

-0.25

]][

-0.25

ä¿±

-0.25

POSITIVE LOGITS

 confront

0.25

act

0.24

 equilibrium

0.24

ç«¯

0.24

 layers

0.24

Mother

0.24

tty

0.24

 Wednesday

0.24

mak

0.24

å¹Į

0.23

Activations Density 0.016%

gender

No Comments

No Known Activations